Remote Frontier AI Security Analyst (Contract)

Alignerr Corp.; New York (NY); On-site; USD 55,000 - 124,000; Part time

Benefits offered by this job

Flexible scheduling

Remote work

Job summary

Alignerr is seeking AI Security Analysts to probe frontier AI models for vulnerabilities, focusing on real-world adversarial scenarios, data leakage, and prompt injection. This fully remote, flexible hourly contract role offers 10–40 hours/week and the autonomy to work on high-impact security challenges with world-leading research labs.

Ideal candidates have a cybersecurity background, strong threat modeling skills, and a disciplined, independent work style, with hands-on AI/LLM experience being

Qualifications

• Background in cybersecurity or information security.
• Understanding of security threat modeling applied to AI.
• Ability to analyze complex systems and edge cases.

Responsibilities

• Analyze real-world AI and LLM security scenarios to understand how models behave under adversarial or unexpected conditions.
• Review and evaluate cases involving prompt injection, data leakage, model abuse, and system misuse.
• Classify security issues by real-world impact and likelihood, and recommend appropriate mitigations.
• Help evaluate and improve AI system behavior so it remains safe, reliable, and aligned with security best practices.
• Work independently and asynchronously — on your own schedule, at your own pace.

Skills

Cybersecurity

Threat modeling

Analytical thinking

Independent work

AI familiarity

Education

Background in cybersecurity or information security

Job description

Alignerr is seeking AI Security Analysts to probe frontier AI models for vulnerabilities, focusing on real-world adversarial scenarios, data leakage, and prompt injection. This fully remote, flexible hourly contract role offers 10–40 hours/week and the autonomy to work on high-impact security challenges with world-leading research labs.

Ideal candidates have a cybersecurity background, strong threat modeling skills, and a disciplined, independent work style, with hands-on AI/LLM experience being